bandicoot is an open-source python toolbox to analyze and extract behavioral indicators from mobile phone data. It is developed by Yves-Alexandre de Montjoye, Luc Rocher and Alex Pentland at the MIT Media Lab (Human Dynamics Group).
The behavioral indicators computed by bandicoot have already been used to release data as part of Orange D4D Challenge, to predict gender, age, and personality; and for customer segmentation.
If you use bandicoot in your research please cite it as:
Note
de Montjoye, Y. A., Rocher, L., & Pentland, A. S. (2016). bandicoot: a Python Toolbox for Mobile Phone Metadata. Journal of Machine Learning Research, 17(175), 1-5.
.. toctree::
:maxdepth: 2
quickstart
using_bandicoot
reference/index
developers
data_integrity